Research map / Architectures and efficiency / RNNs and normalization
Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
Yingru Liu, Xuewen Yang, Dongliang Xie, Xin Wang, Li Shen, Haozhi Huang, Niranjan Balasubramanian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cosine-similarity functional regularization (ablation) | TAAN · YouTube-8M | Mean mAP%10: 0.842 -> 0.860 | Improved |
| add distance functional regularization (ablation) | TAAN · YouTube-8M | Mean mAP%10: 0.842 -> 0.851 | Improved |
| add trace-norm regularization (ablation) | TAAN · YouTube-8M | Mean mAP%10: 0.842 -> 0.749 | Hurt |
| add cosine-similarity functional regularization (ablation) | TAAN · Omniglot | Accuracy | No clear effect |
| add distance functional regularization (ablation) | TAAN · Omniglot | Accuracy | Improved |
| add trace-norm regularization (ablation) | TAAN · Omniglot | Accuracy | Hurt |
| use task-adaptive activations with shared weights and biases instead of Soft-Order | multi-task alphabet classification · Omniglot | Accuracy: 75.89 % -> 84.11 % | Improved |
Closest papers by meaning
- Latent Multi-Task Architecture Learning (AAAI 2019 · similarity 0.87)
- GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (ICML 2018 · similarity 0.86)
- Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies (CVPR 2023 · similarity 0.86)
- Multi-Task Recurrent Modular Networks (AAAI 2021 · similarity 0.86)
- End-To-End Multi-Task Learning With Attention (CVPR 2019 · similarity 0.85)
- MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
